Epilepsy Classification Using Discriminant Analysis and Implementation with Space Time Trellis Coded MIMO-OFDM System for Telemedicine Applications

  • Sunil Kumar Prabhakar
  • Harikumar Rajaguru
Conference paper
Part of the IFMBE Proceedings book series (IFMBE, volume 63)


Epilepsy is one of the major neurological disorders occurring in the brain which causes sudden and recurrent seizures. These seizures cause loss of motor control in the human brain thereby bringing dangerous situations in the life of an epileptic patient. The patients tend to develop anxiety problems throughout their life because the seizures occur without any preliminary warnings. Electroencephalogram (EEG) is used to measure the recordings of the human brain and it helps greatly as a tool for analyzing, recognizing, diagnosing and classifying the epilepsy from EEG signals. Since the recordings are pretty huge, it is quite hectic to process the entire data and therefore certain dimensionality reduction techniques are required to reduce the dimensions of the data. In this paper, the dimensions of the data is reduced with the help of Linear Discriminant Analysis (LDA) and then the dimensionally reduced data is transmitted with the help of Space Time Trellis Coded Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing (STTC MIMO-OFDM) System. At the receiver side, the Expectation Maximization Based Gaussian Mixture Model (EM-GMM) is engaged to classify the epilepsy from EEG signals. Also the Bit Error Rate (BER) is analyzed at the receiver side along with the classification accuracy. The performance measures analyzed here are Specificity, Sensitivity, Time Delay, Quality Values, Performance Index and Accuracy.




Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lippmann RP (1989) Pattern classification using neural networks. IEEE Communication Mag 27(11):47–50CrossRefGoogle Scholar
  2. 2.
    Zhang GP (2000) Neural networks for classification: a survey. IEEE Trans System Man Cybern Part C Appl Rev 30(4):451–462CrossRefGoogle Scholar
  3. 3.
    Kiymik MK, Subasi A, Ozcalik HR (2004) Neural networks with period gram and autoregressive spectral analysis methods in detection of epileptic seizure. J Med Syst 28:511–522CrossRefGoogle Scholar
  4. 4.
    Weng W, Khorasani K (1996) An adaptive structure neural network with application to EEG automatic seizure detection. Neural net 9:1223–1240CrossRefGoogle Scholar
  5. 5.
    Pradhan N, Sadasivan PK, Arunodaya GR (1996) Detection of seizure activity in EEG by an artificial neural network: a preliminary study. Compt Biomed Res 29:313–330Google Scholar
  6. 6.
    Srinivasan V, Eswaran C, Sriaan N (2005) Artificial Neural Network based Epileptic detection using time domain and frequency domain features. J Med syst 29(6):647–660CrossRefGoogle Scholar
  7. 7.
    Kannathal N, Choo ML, Acharya UR, Sadasivan PK (2005) Entropies for detection of epilepsy in EEG. Comput Meth Prog Biomed 80(3):187–194CrossRefGoogle Scholar
  8. 8.
    Polat K, Gunes S (2007) Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Appl Math Comput 32(2):625–631MathSciNetzbMATHGoogle Scholar
  9. 9.
    Subasi A (2007) Signal classification using wavelet feature extraction and a mixture of expert model. Exp Syst Appl 32(4):1084–1093CrossRefGoogle Scholar
  10. 10.
    Fathima T, Khan YU, Bedeeuzzaman M, Farooq O (2011) Discriminant analysis for epileptic seizure detection. In: Proceeding International Conference Devices and Communication, pp 1–5Google Scholar
  11. 11.
    Gu Q, Li Z, Han J (2011) Linear discriminant dimensionality reduction. Machine learning and knowledge discovery in databases, vol 6911 of the series LNCS, pp 549–564 Google Scholar
  12. 12.
    Lozano A et al (2005) High-SNR power offset in multi-antenna communication. In: IEEE international conference communication, pp 4134–4151Google Scholar
  13. 13.
    Chen Z, Yuan J, Vucetic B (2001) Improved space-time trellis coded modulation scheme on slow Rayleigh fading channels. Electron Lett 37:440–441CrossRefGoogle Scholar
  14. 14.
    Prabhakar SK, Rajaguru H (2015) ICA, LGE and FMI as dimensionality reduction techniques followed by Gmm as post classifier for the classification of epilepsy risk levels from EEG signals. In: 9th IEEE European modelling symposium 2015, October 6–8, Madrid, Spain, 978-1-5090-0206-1/15. doi:  10.1109/EMS.2015.20

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of ECEBannari Amman Institute of TechnologySathyamangalamIndia

Personalised recommendations